ES|QL change_point processing command

docs/changelog/120998.yaml

@@ -0,0 +1,5 @@
+pr: 120998
+summary: ES|QL `change_point` processing command
+area: Machine Learning
+type: feature
+issues: []

x-pack/plugin/esql/compute/src/main/java/org/elasticsearch/compute/operator/ChangePointOperator.java

@@ -0,0 +1,207 @@
+/*
+ * Copyright Elasticsearch B.V. and/or licensed to Elasticsearch B.V. under one
+ * or more contributor license agreements. Licensed under the Elastic License
+ * 2.0; you may not use this file except in compliance with the Elastic License
+ * 2.0.
+ */
+
+package org.elasticsearch.compute.operator;
+
+import org.apache.lucene.util.BytesRef;
+import org.elasticsearch.compute.data.Block;
+import org.elasticsearch.compute.data.BlockFactory;
+import org.elasticsearch.compute.data.BlockUtils;
+import org.elasticsearch.compute.data.BytesRefBlock;
+import org.elasticsearch.compute.data.DoubleBlock;
+import org.elasticsearch.compute.data.Page;
+import org.elasticsearch.core.Releasables;
+import org.elasticsearch.xpack.ml.aggs.MlAggsHelper;
+import org.elasticsearch.xpack.ml.aggs.changepoint.ChangePointDetector;
+import org.elasticsearch.xpack.ml.aggs.changepoint.ChangeType;
+
+import java.util.Deque;
+import java.util.LinkedList;
+
+public class ChangePointOperator implements Operator {
+
+    public static final int INPUT_VALUE_COUNT_LIMIT = 1000;
+
+    public record Factory(int channel, String sourceText, int sourceLine, int sourceColumn) implements OperatorFactory {
+        @Override
+        public Operator get(DriverContext driverContext) {
+            return new ChangePointOperator(driverContext, channel, sourceText, sourceLine, sourceColumn);
+        }
+
+        @Override
+        public String describe() {
+            return "ChangePointOperator[channel=" + channel + "]";
+        }
+    }
+
+    private final DriverContext driverContext;
+    private final int channel;
+    private final String sourceText;
+    private final int sourceLine;
+    private final int sourceColumn;
+
+    private final Deque<Page> inputPages;
+    private final Deque<Page> outputPages;
+    private boolean finished;
+    private Warnings warnings;
+
+    public ChangePointOperator(DriverContext driverContext, int channel, String sourceText, int sourceLine, int sourceColumn) {
+        this.driverContext = driverContext;
+        this.channel = channel;
+        this.sourceText = sourceText;
+        this.sourceLine = sourceLine;
+        this.sourceColumn = sourceColumn;
+
+        finished = false;
+        inputPages = new LinkedList<>();
+        outputPages = new LinkedList<>();
+        warnings = null;
+    }
+
+    @Override
+    public boolean needsInput() {
+        return finished == false;
+    }
+
+    @Override
+    public void addInput(Page page) {
+        inputPages.add(page);
+    }
+
+    @Override
+    public void finish() {
+        if (finished == false) {
+            finished = true;
+            createOutputPages();
+        }
+    }
+
+    @Override
+    public boolean isFinished() {
+        return finished && outputPages.isEmpty();
+    }
+
+    @Override
+    public Page getOutput() {
+        if (finished == false || outputPages.isEmpty()) {
+            return null;
+        }
+        return outputPages.removeFirst();
+    }
+
+    private void createOutputPages() {
+        int valuesCount = 0;
+        for (Page page : inputPages) {
+            valuesCount += page.getPositionCount();
+        }
+        boolean tooManyValues = valuesCount > INPUT_VALUE_COUNT_LIMIT;
+        if (tooManyValues) {
+            valuesCount = INPUT_VALUE_COUNT_LIMIT;
+        }
+
+        double[] values = new double[valuesCount];
+        int valuesIndex = 0;
+        boolean hasNulls = false;
+        for (Page inputPage : inputPages) {
+            Block inputBlock = inputPage.getBlock(channel);
+            for (int i = 0; i < inputBlock.getPositionCount() && valuesIndex < valuesCount; i++) {
+                Object value = BlockUtils.toJavaObject(inputBlock, i);
+                if (value == null) {
+                    hasNulls = true;
+                    values[valuesIndex++] = 0;
+                } else {
+                    values[valuesIndex++] = ((Number) value).doubleValue();
+                }
+            }
+        }
+
+        ChangeType changeType = ChangePointDetector.getChangeType(new MlAggsHelper.DoubleBucketValues(null, values));
+        int changePointIndex = changeType.changePoint();
+
+        BlockFactory blockFactory = driverContext.blockFactory();
+        int pageStartIndex = 0;
+        while (inputPages.isEmpty() == false) {
+            Page inputPage = inputPages.peek();
+            Page outputPage;
+            Block changeTypeBlock = null;
+            Block changePvalueBlock = null;
+            boolean success = false;
+            try {
+                if (pageStartIndex <= changePointIndex && changePointIndex < pageStartIndex + inputPage.getPositionCount()) {
+                    try (
+                        BytesRefBlock.Builder changeTypeBlockBuilder = blockFactory.newBytesRefBlockBuilder(inputPage.getPositionCount());
+                        DoubleBlock.Builder pvalueBlockBuilder = blockFactory.newDoubleBlockBuilder(inputPage.getPositionCount())
+                    ) {
+                        for (int i = 0; i < inputPage.getPositionCount(); i++) {
+                            if (pageStartIndex + i == changePointIndex) {
+                                changeTypeBlockBuilder.appendBytesRef(new BytesRef(changeType.getWriteableName()));
+                                pvalueBlockBuilder.appendDouble(changeType.pValue());
+                            } else {
+                                changeTypeBlockBuilder.appendNull();
+                                pvalueBlockBuilder.appendNull();
+                            }
+                        }
+                        changeTypeBlock = changeTypeBlockBuilder.build();
+                        changePvalueBlock = pvalueBlockBuilder.build();
+                    }
+                } else {
+                    changeTypeBlock = blockFactory.newConstantNullBlock(inputPage.getPositionCount());
+                    changePvalueBlock = blockFactory.newConstantNullBlock(inputPage.getPositionCount());
+                }
+
+                outputPage = inputPage.appendBlocks(new Block[] { changeTypeBlock, changePvalueBlock });
+                success = true;
+            } finally {
+                if (success == false) {
+                    Releasables.closeExpectNoException(changeTypeBlock, changePvalueBlock);
+                }
+            }
+
+            inputPages.removeFirst();
+            outputPages.add(outputPage);
+            pageStartIndex += inputPage.getPositionCount();
+        }
+
+        if (changeType instanceof ChangeType.Indeterminable indeterminable) {
+            warnings(false).registerException(new IllegalArgumentException(indeterminable.getReason()));
+        }
+        if (tooManyValues) {
+            warnings(true).registerException(
+                new IllegalArgumentException("too many values; keeping only first " + INPUT_VALUE_COUNT_LIMIT + " values")
+            );
+        }
+        if (hasNulls) {
+            warnings(true).registerException(new IllegalArgumentException("values contain nulls; treating them as zeroes"));
+        }
+    }
+
+    @Override
+    public void close() {
+        for (Page page : inputPages) {
+            page.releaseBlocks();
+        }
+        for (Page page : outputPages) {
+            page.releaseBlocks();
+        }
+    }
+
+    @Override
+    public String toString() {
+        return "ChangePointOperator[channel=" + channel + "]";
+    }
+
+    private Warnings warnings(boolean onlyWarnings) {
+        if (warnings == null) {
+            if (onlyWarnings) {
+                this.warnings = Warnings.createOnlyWarnings(driverContext.warningsMode(), sourceLine, sourceColumn, sourceText);
+            } else {
+                this.warnings = Warnings.createWarnings(driverContext.warningsMode(), sourceLine, sourceColumn, sourceText);
+            }
+        }
+        return warnings;
+    }
+}

x-pack/plugin/esql/compute/src/main/java/org/elasticsearch/compute/operator/Warnings.java

@@ -32,7 +32,7 @@ public void registerException(Exception exception) {
      * @return A warnings collector object
      */
     public static Warnings createWarnings(DriverContext.WarningsMode warningsMode, int lineNumber, int columnNumber, String sourceText) {
-        return createWarnings(warningsMode, lineNumber, columnNumber, sourceText, "treating result as null");
+        return createWarnings(warningsMode, lineNumber, columnNumber, sourceText, "evaluation of [{}] failed, treating result as null");
     }
 
     /**
@@ -50,7 +50,25 @@ public static Warnings createWarningsTreatedAsFalse(
         int columnNumber,
         String sourceText
     ) {
-        return createWarnings(warningsMode, lineNumber, columnNumber, sourceText, "treating result as false");
+        return createWarnings(warningsMode, lineNumber, columnNumber, sourceText, "evaluation of [{}] failed, treating result as false");
+    }
+
+    /**
+     * Create a new warnings object based on the given mode which warns that
+     * evaluation resulted in warnings.
+     * @param warningsMode The warnings collection strategy to use
+     * @param lineNumber The line number of the source text. Same as `source.getLineNumber()`
+     * @param columnNumber The column number of the source text. Same as `source.getColumnNumber()`
+     * @param sourceText The source text that caused the warning. Same as `source.text()`
+     * @return A warnings collector object
+     */
+    public static Warnings createOnlyWarnings(
+        DriverContext.WarningsMode warningsMode,
+        int lineNumber,
+        int columnNumber,
+        String sourceText
+    ) {
+        return createWarnings(warningsMode, lineNumber, columnNumber, sourceText, "warnings during evaluation of [{}]");
     }
 
     private static Warnings createWarnings(
@@ -78,14 +96,7 @@ private static Warnings createWarnings(
 
     private Warnings(int lineNumber, int columnNumber, String sourceText, String first) {
         this.location = format("Line {}:{}: ", lineNumber, columnNumber);
-        this.first = format(
-            null,
-            "{}evaluation of [{}] failed, {}. Only first {} failures recorded.",
-            location,
-            sourceText,
-            first,
-            MAX_ADDED_WARNINGS
-        );
+        this.first = format(null, "{}" + first + ". Only first {} failures recorded.", location, sourceText, MAX_ADDED_WARNINGS);
     }
 
     public void registerException(Exception exception) {

x-pack/plugin/esql/compute/src/test/java/org/elasticsearch/compute/operator/ChangePointOperatorTests.java

@@ -0,0 +1,86 @@
+/*
+ * Copyright Elasticsearch B.V. and/or licensed to Elasticsearch B.V. under one
+ * or more contributor license agreements. Licensed under the Elastic License
+ * 2.0; you may not use this file except in compliance with the Elastic License
+ * 2.0.
+ */
+
+package org.elasticsearch.compute.operator;
+
+import org.apache.lucene.util.BytesRef;
+import org.elasticsearch.compute.data.BlockFactory;
+import org.elasticsearch.compute.data.BytesRefBlock;
+import org.elasticsearch.compute.data.DoubleBlock;
+import org.elasticsearch.compute.data.LongBlock;
+import org.elasticsearch.compute.data.Page;
+import org.elasticsearch.compute.test.OperatorTestCase;
+import org.elasticsearch.compute.test.SequenceLongBlockSourceOperator;
+import org.hamcrest.Matcher;
+
+import java.util.ArrayList;
+import java.util.List;
+
+import static org.hamcrest.Matchers.equalTo;
+import static org.hamcrest.Matchers.hasSize;
+
+public class ChangePointOperatorTests extends OperatorTestCase {
+
+    @Override
+    protected SourceOperator simpleInput(BlockFactory blockFactory, int size) {
+        // size must be in [25, 1000] for ChangePoint to function correctly
+        // and detect the step change.
+        size = Math.clamp(size, 25, 1000);
+        List<Long> data = new ArrayList<>(size);
+        for (int i = 0; i < size; i++) {
+            if (i <= size / 2) {
+                data.add(0L);
+            } else {
+                data.add(1L);
+            }
+        }
+        return new SequenceLongBlockSourceOperator(blockFactory, data);
+    }
+
+    @Override
+    protected void assertSimpleOutput(List<Page> input, List<Page> results) {
+        boolean seenOne = false;
+        assertThat(results, hasSize(input.size()));
+        for (int i = 0; i < results.size(); i++) {
+            Page inputPage = input.get(i);
+            Page resultPage = results.get(i);
+            assertThat(resultPage.getPositionCount(), equalTo(inputPage.getPositionCount()));
+            assertThat(resultPage.getBlockCount(), equalTo(3));
+            for (int j = 0; j < resultPage.getPositionCount(); j++) {
+                long inputValue = ((LongBlock) resultPage.getBlock(0)).getLong(j);
+                long resultValue = ((LongBlock) resultPage.getBlock(0)).getLong(j);
+                assertThat(resultValue, equalTo(inputValue));
+                if (seenOne == false && resultValue == 1L) {
+                    BytesRef type = ((BytesRefBlock) resultPage.getBlock(1)).getBytesRef(j, new BytesRef());
+                    double pvalue = ((DoubleBlock) resultPage.getBlock(2)).getDouble(j);
+                    assertThat(type.utf8ToString(), equalTo("step_change"));
+                    assertThat(pvalue, equalTo(0.0));
+                    seenOne = true;
+                } else {
+                    assertThat(resultPage.getBlock(1).isNull(j), equalTo(true));
+                    assertThat(resultPage.getBlock(2).isNull(j), equalTo(true));
+                }
+            }
+        }
+        assertThat(seenOne, equalTo(true));
+    }
+
+    @Override
+    protected Operator.OperatorFactory simple() {
+        return new ChangePointOperator.Factory(0, null, 0, 0);
+    }
+
+    @Override
+    protected Matcher<String> expectedDescriptionOfSimple() {
+        return equalTo("ChangePointOperator[channel=0]");
+    }
+
+    @Override
+    protected Matcher<String> expectedToStringOfSimple() {
+        return equalTo("ChangePointOperator[channel=0]");
+    }
+}

x-pack/plugin/esql/compute/test/src/main/java/org/elasticsearch/compute/test/OperatorTestCase.java

@@ -46,7 +46,6 @@
 
 import static org.hamcrest.Matchers.empty;
 import static org.hamcrest.Matchers.equalTo;
-import static org.hamcrest.Matchers.in;
 
 /**
  * Base tests for {@link Operator}s that are not {@link SourceOperator} or {@link SinkOperator}.